Spearman rho
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
MIRAI: Prediction and Generation of High-Impact Academic Research
arXiv:2606.05443v1 Announce Type: new Abstract: The rapid pace of scientific publishing has made the identification and synthesis of high-impact work an increasingly urgent challenge. We introduce MIRAI (Multi-year Inference of Research trends and Academic Impact), a deep learning framework that predicts paper impact using only it's title, abstract, and publication date. We train MIRAI on the arXiv academic graph to predict 5-year PageRank and citation counts, achieving Spearman's $\rho$ of...
Genomic-Adjusted Radiation Dose from Bulk RNA Sequencing for Personalized Radiotherapy
Radiotherapy is delivered to more than half of all patients with cancer yet is prescribed using uniform physical doses despite well-established interpatient variability in biological response. The genomic-adjusted radiation dose (GARD), derived from the radiosensitivity index (RSI), integrates tumor transcriptomics with radiation dose to estimate patient-specific treatment effect, and has been clinically validated as a predictor of radiotherapy benefit across diverse disease sites, including...
Before and After Temperature: A Distributional View of Creative LLM Generation
arXiv:2606.01451v1 Announce Type: new Abstract: Reference-free evaluation of large language model (LLM) creativity relies on perplexity, entropy, and top-1 margin. We show that a much stronger signal lives one step earlier in the pipeline: in how sampling temperature \emph{reshapes} the model's token distribution before the next token is drawn. On Llama-3.1-8B-Instruct generations of 500 open-ended creative prompts at $T \in \{0.3, 0.8, 1.5\}$, a single per-token feature derived from this...
Expressibility, Noise, and Error Mitigation in VQE Ansatz Selection
arXiv:2606.04955v1 Announce Type: cross Abstract: The variational quantum eigensolver (VQE) is a promising algorithm for near-term quantum chemistry applications, but selecting optimal ansatz circuits remains challenging. Expressibility, a metric quantifying a circuit's ability to explore the Hilbert space, has been proposed as a guide for ansatz selection, but recent work showed it inconsistently predicts VQE performance under realistic noise for $H_2$. We extend this investigation to cover...
EndoTwin-W: glycodelin-A and CA-125 as non-invasive biomarkers of endometrial receptivity derived from a multiscale computational digital twin
Endometrial receptivity assessment currently requires invasive tissue biopsy, yet recent randomized trials have questioned the clinical utility of biopsy-based approaches. Here we present EndoTwin-W, a four-layer mechanistic computational model that simulates human endometrial remodeling from hormone inputs through receptor binding, pathway scoring, and continuous-time Markov chain cell-state transitions across 17 cell states. Transition rates were optimized against scRNA-seq and microarray...
On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders
arXiv:2605.31518v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) decompose neural network activations into interpretable features, but many learned features never activate, a problem called feature death that wastes dictionary capacity and can reintroduce superposition. Death rates vary dramatically between models: near-zero on GPT-2, over 70% on AlphaFold3 with identical configurations. We find that dimension-level activation outliers (dimensions whose mean magnitude is large...
Explainable AI Through a Democratic Lens: DhondtXAI for D'Hondt-Projected Feature Attribution
arXiv:2411.05196v3 Announce Type: replace Abstract: This study presents DhondtXAI as a SHAP-independent, D'Hondt-based attribution framework for tabular XAI. Instead of model-native feature importance or SHAP values, DhondtXAI computes background-interventional removal effects, separates positive and negative evidence, forms optional feature alliances, applies optional thresholds, allocates seats via the D'Hondt rule, and projects onto the local model-output difference. Completeness is...
Efficient Benchmarking Is Just Feature Selection and Multiple Regression
Announce Type: replace-cross Abstract: Efficient benchmarking techniques aim to lower the computational cost of evaluating LLMs by predicting full benchmark scores using only a subset of a benchmark's questions. By reframing this problem as an instance of multiple regression with feature selection, we find that existing efficient benchmarking methods can be greatly improved by simply using kernel ridge regression at the prediction stage. Additionally, using an information-theoretic...
Predicting Inference-Time Scaling Gains from Labeled Validation-Set Output Statistics
arXiv:2606.02981v1 Announce Type: new Abstract: Best-of-$N$ inference scaling (drawing $N$ candidate answers from a language model and returning the one a reward model ranks highest) improves accuracy by an amount that varies across models, but predicting that amount in advance currently requires running the procedure end-to-end. Prior work links cheap statistics of a model's sampled outputs and validation-set correctness (how often samples agree, how diverse they are, how confident the...
Zero-Parameter Geometric Gating for Temporally Stable Low-Altitude UAV Video Semantic Segmentation
Announce Type: new Abstract: Video semantic segmentation for low-altitude UAVs requires temporal consistency, yet dense optical flow introduces spatially structured noise in the planar regions that dominate aerial imagery. We propose a zero-parameter geometric gate that uses RANSAC homography inlier ratios on a $16\times16$ spatial grid to route each region to either homography or optical flow warp before fusion via Semantic Similarity Propagation. The gate requires no learned parameters --...